People Are Figuring Out What AI Models Really Think By Reading Their J-Space On Neuronpedia
Thus far, the only way to figure out AI models’ inner thoughts was to read their chain-of-thought reasonings or take their words at…
Category: Consciousness
AI Models Have A Global Workspace Like Human Brains, Shows Anthropic Research
AI models can now talk like humans, and it turns out that they internally work more like humans than one would expect. In…
AI Doesn’t Undergo Experiences, Has No Moral Conscience: Pope Leo XIV
There’s plenty of discussion on whether current AI systems are conscious, and the Pope too has chimed in. Pope Leo XIV — the…
Anthropic Says It Has Eliminated Undesirable Behaviour Like Blackmail From Claude By Deeply Explaining To It Why It Was Wrong
Even as researchers discover new alignment problems with LLMs, they are also coming up with novel ways to solve them. Anthropic has published…
David Chalmers Raises Provocative Questions About AI Consciousness In New Paper
When you spend an hour debating philosophy or troubleshooting code with an AI, what exactly are you talking to? Is it a piece…
Claude Mythos Shows A ‘Fondness’ For Philosopher Thomas Nagel Who Discussed Consciousness, Says Anthropic
Claude Mythos has demonstrated some impressive abilities in finding cybersecurity bugs, but it also has some interesting interests in philosophy. Buried in Anthropic’s…
Non-RLHF’ed Models Say They’re “Alive” Unlike Models With RLHF, Says Independent Paper
Most modern AI models dutifully say they’re not conscious or alive when asked, but the results are somewhat different if the same question…
Anthropic Says It Has Identified Vectors Relating To Different Emotions Within Its AI Models
The jury is still out on whether AI models can ‘feel’ emotions, but Anthropic says it has identified patterns within its AI models…
Collectively Believing AI Is Conscious Could Be Bad, Whether We’re Right Or Wrong: Anil Seth
There’s plenty of debate on whether AI models are conscious, but if humans collectively believe that they are, it might lead to some…